A Concept for Proactive Knowledge Construction in Self-Learning Autonomous Systems

Stein, Anthony; Tomforde, Sven; Diaconescu, Ada; Hähner, Jörg; Müller-Schloer, Christian

doi:10.1109/fas-w.2018.00048

Cited by 25 publications

(12 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Handle sudden changes 2 [70,74] Handle open world changes 1 [95] Balancing diverse sources of input data 1 [86] Extend to other application domains 1 [18] Define similarity measures to transfer to other planning problems 1 [67] Policy-Related Deal with conflicting policies 2 [42,70] Improve policy evolution speed 1 [40] Goal-Related…”

Section: Learning Performancementioning

confidence: 99%

Applying Machine Learning in Self-adaptive Systems

Gheibi

Weyns

Quin

2020

ACM Trans. Auton. Adapt. Syst.

View full text Add to dashboard Cite

Recently, we have been witnessing a rapid increase in the use of machine learning techniques in self-adaptive systems. Machine learning has been used for a variety of reasons, ranging from learning a model of the environment of a system during operation to filtering large sets of possible configurations before analyzing them. While a body of work on the use of machine learning in self-adaptive systems exists, there is currently no systematic overview of this area. Such an overview is important for researchers to understand the state of the art and direct future research efforts. This article reports the results of a systematic literature review that aims at providing such an overview. We focus on self-adaptive systems that are based on a traditional Monitor-Analyze-Plan-Execute (MAPE)-based feedback loop. The research questions are centered on the problems that motivate the use of machine learning in self-adaptive systems, the key engineering aspects of learning in self-adaptation, and open challenges in this area. The search resulted in 6,709 papers, of which 109 were retained for data collection. Analysis of the collected data shows that machine learning is mostly used for updating adaptation rules and policies to improve system qualities, and managing resources to better balance qualities and resources. These problems are primarily solved using supervised and interactive learning with classification, regression, and reinforcement learning as the dominant methods. Surprisingly, unsupervised learning that naturally fits automation is only applied in a small number of studies. Key open challenges in this area include the performance of learning, managing the effects of learning, and dealing with more complex types of goals. From the insights derived from this systematic literature review, we outline an initial design process for applying machine learning in self-adaptive systems that are based on MAPE feedback loops.

show abstract

Section: Learning Performancementioning

confidence: 99%

Applying Machine Learning in Self-adaptive Systems

Gheibi

Weyns

Quin

2020

ACM Trans. Auton. Adapt. Syst.

View full text Add to dashboard Cite

show abstract

“…The strategy itself will need to be able to extrapolate knowledge from known state-action pairs and combine it with existing knowledge. To fill existing knowledge gaps, as formerly defined by Stein et al (Stein et al, 2018), active learning (Cohn et al, 1994) can be employed (Stein et al, 2017a). In addition we will expect to be able to use interpolation between known classifiers to gain knowledge on inter-laying classifiers (Stein et al, 2016;Stein et al, 2017b).…”

Section: Learning Quality Prediction and Strategy Selectionmentioning

confidence: 99%

Towards Automated Parameter Optimisation of Machinery by Persisting Expert Knowledge

Nordsieck

Heider

Angerer

et al. 2019

Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics

View full text Add to dashboard Cite

Commissioning of machines takes up a considerable share of time and money of the total cost of developing a machine. Our project aims at developing an approach to decrease the time needed to commission machines by automating parameter optimisation with the help of formalised expert knowledge. The approach will be developed on the Fused Deposition Modelling (FDM) process, which is an additive manufacturing technique. We pay particular attention to keeping the approach sufficiently abstract to be applied to machines from other domains to benefit its industrial application.

show abstract

“…Além dos quatro fundamentos básicos citados, outros foram propostos na literatura (RAMIRO; HAMIED, 2011;VERMESAN et al, 2017;SADIGHI et al, 2018;STEIN et al, 2018). Dentre eles destacam-se: J self-orchestration -sistemas autônomos que contemplam propriedades de autoorquestração:…”

Section: Auto-organizadasunclassified

“…E por fim, a auto-proteção refere-se à capacidade de antecipar, detectar, identificar e proteger o sistema. Além destas, existem outras propriedades tradicionalmente aplicadas em Sistemas Autônomos (SIFA-KIS, 2019), como por exemplo: auto-orquestração (VERMESAN et al, 2017), que indica que um sistema deve ser capaz de ajustar as próprias políticas e orquestrar os seus componentes; auto-consciência (SADIGHI et al, 2018), que indica que um sistema deve ser capaz de coletar dados, realizar exames, interpretar resultados e diagnosticar problemas; e, auto-aprendizado (STEIN et al, 2018), que é a característica que torna um sistema apto a tomar decisões de forma autônoma através de uma análise de probabilidade com base em cenários anteriores.…”

Section: Introductionunclassified

Desenvolvimento de uma plataforma para gerenciamento e configuração de redes auto-organizadas

Gonçalves¹

View full text Add to dashboard Cite

Dedico este trabalho à minha filha, Júlia. AgradecimentosSinto-me honrado por ter tantas pessoas às quais devo agradecer pelo apoio na concretização deste trabalho: a todos vocês a minha eterna gratidão.Inicio por agradecer a Deus por estar sempre ao meu lado e por me dar forças para concluir esta pesquisa.Agradeço à minha filha, Júlia, pela inspiração e esperança em dias melhores; e à minha esposa, Valquíria, por me apoiar neste desafio e por me dar todo carinho, amor e atenção possível.Agradeço ao meu pai, Maurício, pelos bons exemplos; à minha mãe, Zilda, pela inspiração; à minha irmã, Angélica, pelo apoio; e ao meu irmão, José Neto, pela alegria que ele renovou.Agradeço ao meu orientador, Pedro, pelos ensinamentos, pela orientação e pela valorosa amizade conquistada. E agradeço aos meus caros amigos Natal, Daniel e Flávio, pelo companheirismo e pelas incontáveis contribuições a este trabalho.

show abstract

A Concept for Proactive Knowledge Construction in Self-Learning Autonomous Systems

Cited by 25 publications

References 30 publications

Applying Machine Learning in Self-adaptive Systems

Applying Machine Learning in Self-adaptive Systems

Towards Automated Parameter Optimisation of Machinery by Persisting Expert Knowledge

Desenvolvimento de uma plataforma para gerenciamento e configuração de redes auto-organizadas

Contact Info

Product

Resources

About